GPT Image 2.5 Sunburst
openai/gpt-image-2.5/sunburst/edit- OpenAI
- Image to image
- Image
Edit a reference image with a text instruction.
Overview
- Model developer
- OpenAI
- API channel
- fal.ai
- Supported protocols
fal-task
Call this model
Create an API key, add account credit, and confirm this model is available to your key before sending a request.
Asynchronous image and video generation
Submit once to receive a task_id immediately. Keep SCENEPOND_API_KEY in your server environment.
1. Submit a task
This example uses the model defaults. Optional settings belong in parameters and follow the selected model schema.
Replace https://example.com/reference.png with a publicly accessible reference image URL before submitting.
1curl --fail-with-body "https://scenepond-api-production.up.railway.app/v1/tasks/fal" \
2 -H "Authorization: Bearer $SCENEPOND_API_KEY" \
3 -H "Content-Type: application/json" \
4 --data-binary @- <<'JSON'
5{
6 "model": "openai/gpt-image-2.5/sunburst/edit",
7 "prompt": "A quiet lakeside at sunrise",
8 "images": [
9 "https://example.com/reference.png"
10 ]
11}
12JSONRun this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.
2. Check task status
Set SCENEPOND_TASK_ID to the returned task_id. Repeat this query every few seconds until status is SUCCESS or FAILURE. On FAILURE, read fail_reason; a new submission creates a new task.
1curl --fail-with-body "https://scenepond-api-production.up.railway.app/v1/tasks/$SCENEPOND_TASK_ID" \
2 -H "Authorization: Bearer $SCENEPOND_API_KEY"Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.
3. Get the results
After SUCCESS, list the artifacts and open each content_url to retrieve the generated image or video.
1curl --fail-with-body "https://scenepond-api-production.up.railway.app/v1/tasks/$SCENEPOND_TASK_ID/artifacts" \
2 -H "Authorization: Bearer $SCENEPOND_API_KEY"Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.
Use it in your application
Use the task API in your application to submit generation requests and retrieve results by task ID.
Model access and request limits depend on your account, API key, and service configuration.